基于小波消噪的ARIMA与SVM组合交通流预测

针对实际交通系统时变复杂和变化的不确定性所带来的交通流量非线性和强干扰性的特征,首先应用小波分析方法,对原始交通数据进行了消噪处理,使消噪后的数据更能反映交通流的本质及变化规律;然后采用自回归求和滑动平均(ARIMA)和支持向量机(SVM)的结合预测模型对交通流进行了预测,最后用实测交通数据进行了验证分析,得到了两个结论:一是组合预测模型比单个预测模型的预测精度高;二是小波分析消噪后的组合预测模型比没有消噪的组合预测模型预测精度高.结果表明消噪后的组合预测模型具有较高的预测精度,可用于交通流的实时动态预测.     

基于小波变换的多分辨率图像转换

为适应不同设备、不同信道和不同应用的要求,数字图像处理中需要改变图像的空间分辨率。传统的改变图像空间分辨率的办法是抽取和线性插值。本文基于小波分析提出由高分辨率图像可得到各种较低分辨率图像的多分辨方法符合人的视觉系统特性。为了提高图像的空间分辨率,本文根据小波子带间的相关性等特点,提出由低分辨率的高频细节预测高分辨率的高频细节方法,从理论分析到实验结果,均表明本文方法是可行的,而且优于传统的方法。     

基于微机监控系统电容型设备介损在线测量研究

为了提高电容型设备介损在线监测方法的测量精度和实现智能化管理,探讨利用微机监控系统进行管理的方法,重点介绍了系统的组成、工作原理和相关技术措施.     

机械设备故障诊断理论及相关技术的研究

对应用于机械设备故障诊断方面的理论及相关技术的发展及现状进行了研究,针对各种故障诊断方法探讨了其优缺点及其适应性,研究了小波(Wavelet)分析的发展及其在机械故障诊断中的应用。     

道路货物运输企业如何向物流企业转化

论述了道路货物运输企业向物流企业转化的必要性,分析了道路货物运输企业向物流 企业转化的有利条件,以及转化中可能存在的困难与难点,对道路货物运输企业如何向物流转 化提出了几点建议;最后,指出了道路货物运输企业向物流企业转化中应注意的几个问题.     

AN FFT-BASED SELF-SIMILAR TRAFFIC GENERATOR

IntroductionWhen modeling network traffic,packet ar-rivals are often assumed to be Poisson processes,because such processes have attractive theoreticalproperties. Recenet work,however,argues con-vincingly that local- area network traffic is muchbetter modeled using statistically self- similar pro-cesses[1] ,which have more different theoreticalproperties than Poisson processes. A subsequentinvestigation suggests that the same holds forwide- area network traffic[2 ,3 ] .The theory of self- sim…     

基于整数提升小波和Rice编码的机车信号波形数据的无损压缩方法

针对铁路现场机车信号实际运用情况,提出了一种基于整数提升小波变换和Rice编码的机车信号记录波形数据的无损压缩方法.该方法利用提升结构的整数小波原位运算实现对信号波形数据的快速预测和更新,再对变换后的数据进行Rice无损压缩编码.实验证明,该方法能够达到对机车信号记录器波形数据进行快速、高效的无损压缩存储的要求.     

A new time-frequency analysis method based on single mode function decomposition for offshore wind turbines

The Hilbert-Huang transform (HHT) has been widely applied and recognised as a powerful time-frequency analysis method for nonlinear and non-stationary signals in numerous engineering fields. One of its major challenges is that the HHT is frequently subject to mode mixing in the processing of practical signals such as those of offshore wind turbines, as the frequencies of offshore wind turbines are typically close and contaminated by noise. To address this issue, this paper proposes a new time-frequency analysis method based on single mode function (SMF) decomposition to overcome the mode mixing problem in the structural health monitoring (SHM) of offshore wind turbines. In this approach, the structural vibration signal is first decomposed into a set of window components using complex exponential decomposition. A state-space model is introduced in the signal decomposition to improve the numerical stability of the decomposition, and then a novel window-alignment strategy, named energy gridding, is proposed and the signals are constructed in the corresponding gridding. Furthermore, energy recollection is implemented in each gridding, and the reassembling of these components yields an SMF that is comparable to the intrinsic mode function (IMF) of the HHT, but with a significant improvement in terms of mode mixing. Four case studies are conducted to evaluate the performance of the proposed method. The first case attempts to detect three different frequencies in a simulated time-invariant signal. The second case attempts to test a synthesised signal with segmental time-varying frequencies (each segment contains three different frequencies components). The analysis results in these two cases indicate that mode mixing can be reduced by the proposed method. Furthermore, a synthesised signal with slowly varying frequencies is used. These analysis results demonstrate the effective suppression of non-relevant frequency components using SMF decomposition. In the third case, the experimental data from vortex-induced vibration (VIV) experiments sponsored by the Norwegian Deepwater Programme (NDP) are used to evaluate the proposed SMF decomposition for vibration mode identification. In the final case, field data acquired from an offshore wind turbine foundation and offshore wind turbine are analysed. The mode identification results obtained using SMF decomposition are compared with those produced by the HHT. The comparison demonstrates superior performance of the proposed method in identifying the vibration modes of the VIV experimental and field data.     

小波变换检测铁路交流计数信号的研究

傅氏变换在频域能对信号整体作频谱分析,很难直接分析交流计数信号。近年来兴起的子波变换可对信号进行多尺度分析,容易提取信号特征。本文是用子波变换方法分析铁路交流计数信号。并且通过采用不同的小波基对铁路交流计数信号进行仿真,通过分析比较找到合适的小波基,结合频谱分析的方法得到铁路交流计数信号的有关参数。最后给出仿真的例子。     

小波分析在高压输电线路故障诊断中的应用

运用小波理论,提出了一种新方法,准确地捕捉故障发生时的突变信号,并结合行波故障检测和测距理论,计算出故障距离.给出了算法及仿真结果.